Spark: Modular Spiking Neural Networks

TL;DR

Spark introduces a modular framework for spiking neural networks aimed at improving efficiency and streamlining development, demonstrated through solving a control problem with simple plasticity mechanisms.

Contribution

The paper presents a novel modular framework for spiking neural networks that facilitates efficient development and learning, bridging the gap with traditional machine learning pipelines.

Findings

Successfully applied to the sparse-reward cartpole problem

Utilizes simple plasticity mechanisms for learning

Aims to accelerate research in continuous and unbatched learning

Abstract

Nowadays, neural networks act as a synonym for artificial intelligence. Present neural network models, although remarkably powerful, are inefficient both in terms of data and energy. Several alternative forms of neural networks have been proposed to address some of these problems. Specifically, spiking neural networks are suitable for efficient hardware implementations. However, effective learning algorithms for spiking networks remain elusive, although it is suspected that effective plasticity mechanisms could alleviate the problem of data efficiency. Here, we present a new framework for spiking neural networks - Spark - built upon the idea of modular design, from simple components to entire models. The aim of this framework is to provide an efficient and streamlined pipeline for spiking neural networks. We showcase this framework by solving the sparse-reward cartpole problem with simple plasticity mechanisms. We hope that a framework compatible with traditional ML pipelines may accelerate research in the area, specifically for continuous and unbatched learning, akin to the one animals exhibit.